1          OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK;
 61         
 62         /* mathlogreg3.sas */
 63         
 64         /* Goal: Develop a prediction model that uses all the data and makes a
 65            prediction for every case. */
 66         
 67         %include '/folders/myfolders/441s18/Lecture/mathread1.sas';
 NOTE: Format YNFMT is already on the library WORK.FORMATS.
 NOTE: Format YNFMT has been output.
 NOTE: Format CRSFMT is already on the library WORK.FORMATS.
 NOTE: Format CRSFMT has been output.
 NOTE: Format NFMT is already on the library WORK.FORMATS.
 NOTE: Format NFMT has been output.
 
 NOTE: PROCEDURE FORMAT used (Total process time):
       real time           0.00 seconds
       cpu time            0.00 seconds
       
 
 181        title2 'Use missing values for prediction';
 182        
 183        /* Make missing data indicators */
 
 NOTE: The infile '/folders/myfolders/441s18/Lecture/exploremath.data.txt' is:
       Filename=/folders/myfolders/441s18/Lecture/exploremath.data.txt,
       Owner Name=root,Group Name=vboxsf,
       Access Permission=-rwxrwx---,
       Last Modified=18Jan2016:17:34:49,
       File Size (bytes)=44583
 
 NOTE: 579 records were read from the infile '/folders/myfolders/441s18/Lecture/exploremath.data.txt'.
       The minimum record length was 75.
       The maximum record length was 75.
 NOTE: Missing values were generated as a result of performing an operation on missing values.
       Each place is given by: (Number of times) at (Line):(Column).
       99 at 104:24   99 at 105:18   
 NOTE: The data set WORK.MATHEX has 579 observations and 25 variables.
 NOTE: DATA statement used (Total process time):
       real time           0.02 seconds
       cpu time            0.00 seconds
       
 184        data mathex2;
 
 185             set mathex;
 186             if gender   = . then sexmiss    = 1; else sexmiss=0; /* Includes mtongue */
 187             if course   = . then coursemiss = 1; else coursemiss=0;
 188             if hsgpa    = . then hsgpamiss  = 1; else hsgpamiss=0;
 189             if hscalc   = . then hscalcmiss = 1; else hscalcmiss=0;
 190             if hsengl   = . then hsenglmiss = 1; else hsenglmiss=0;
 191             if totscore = . then testmiss   = 1; else testmiss=0;
 192             if hsgpa+hscalc+precalc = . then missused = 1 ; else missused = 0;
 193             nmiss = sum(sexmiss--testmiss);
 194        
 195        
 196             format sexmiss -- missused ynfmt.;
 197             label sexmiss    = 'Gender and mother tongue missing'
 198                   coursemiss = 'Course missing'
 199                   hsgpamiss  = 'HS GPA missing'
 200                   hscalcmiss = 'HS Calculus mark missing'
 201                   hsenglmiss = 'HS English mark missing'
 202                   testmiss   = 'Diagnostic test scores missing'
 203                   missused   = 'Any of hsgpa hscalc precalc missing';
 204        
 205        /* Checks are commented out
 206        proc freq;
 207             tables gender*sexmiss / norow nocol nopercent missing;
 208             tables course*coursemiss / norow nocol nopercent missing;
 209             tables hsgpa*hsgpamiss / norow nocol nopercent missing;
 210             tables hscalc*hscalcmiss / norow nocol nopercent missing;
 211             tables hsengl*hsenglmiss / norow nocol nopercent missing;
 212             tables totscore*testmiss / norow nocol nopercent missing;
 213             tables (hsgpamiss hscalcmiss testmiss)*missused
 214                                      / norow nocol nopercent missing;
 215        */
 216        
 
 NOTE: Missing values were generated as a result of performing an operation on missing values.
       Each place is given by: (Number of times) at (Line):(Column).
       142 at 192:14   204 at 192:21   
 NOTE: There were 579 observations read from the data set WORK.MATHEX.
 NOTE: The data set WORK.MATHEX2 has 579 observations and 33 variables.
 NOTE: DATA statement used (Total process time):
       real time           0.00 seconds
       cpu time            0.01 seconds
       
 217        proc freq;
 
 218             title2 'Check usefulness of missing data indicators one at a time';
 219             tables (sexmiss -- missused nmiss) * passed / nocol nopercent chisq;
 220        run;
 
 NOTE: There were 579 observations read from the data set WORK.MATHEX2.
 NOTE: PROCEDURE FREQ used (Total process time):
       real time           0.30 seconds
       cpu time            0.30 seconds
       
 
 221        
 222        proc freq;
 223             title2 'Missingness on variables used, and passing the course';
 224             tables missused * passed / norow nocol chisq;
 225        run;
 
 NOTE: There were 579 observations read from the data set WORK.MATHEX2.
 NOTE: PROCEDURE FREQ used (Total process time):
       real time           0.06 seconds
       cpu time            0.06 seconds
       
 
 226        
 227        proc freq;
 228             title2 'Just those with missing on variables used';
 229             where missused = 1;
 230             tables (sexmiss coursemiss) * passed / norow nocol chisq;
 231        run;
 
 NOTE: There were 204 observations read from the data set WORK.MATHEX2.
       WHERE missused=1;
 NOTE: PROCEDURE FREQ used (Total process time):
       real time           0.09 seconds
       cpu time            0.09 seconds
       
 
 232        
 233        /* Decision: If missing on hsgpa, hscalc or precalc, predict they will
 234           not pass. If not missing, use the model with hsgpa, hscalc and precalc. */
 235        
 236        
 237        
 238        
 239        
 240        
 241        
 242        OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK;
 255